© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 22305
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking care of someone or something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to caregiving and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aye
    -0.86
     guiActiveUn
    -0.86
     Cosponsors
    -0.83
    ierre
    -0.80
    oras
    -0.72
    Cola
    -0.71
    clair
    -0.69
    aber
    -0.69
    ãĥ¯ãĥ³
    -0.68
     Zup
    -0.68
    POSITIVE LOGITS
     upkeep
    0.79
     affairs
    0.76
     wellbeing
    0.75
     welfare
    0.66
    ersive
    0.66
    bred
    0.66
     ware
    0.65
    ettes
    0.63
     tending
    0.63
     preservation
    0.60
    Activations Density 0.106%

    No Known Activations